delete_questions
AI agents call delete_questions to permanently remove resources in Xiaoya Teacher — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool deletes questions, which are educational content assets likely created by or managed by the teacher. Deletion is irreversible and represents permanent data loss. Although the description is empty, the name unambiguously indicates a destructive operation. In an educational context, accidentally deleting many questions could disrupt lesson planning and assessment workflows, justifying 'high' severity.
From the tool's definition Tool name: 'delete_questions' - the verb 'delete' is explicitly destructive, indicating irreversible removal of data.
Attacks that exploit this kind of access
delete_questions. It is categorised as a Destructive tool in the Xiaoya Teacher MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Xiaoya Teacher MCP server in PolicyLayer and add a rule for delete_questions: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Xiaoya Teacher. Nothing to install.
delete_questions is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_questions rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for delete_questions. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
delete_questions is provided by the Xiaoya Teacher MCP server (sav1our520/xiaoya-teacher-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →